Github user jkbradley commented on a diff in the pull request:

    https://github.com/apache/spark/pull/17373#discussion_r133082607
  
    --- Diff: 
mllib/src/test/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifierSuite.scala
 ---
    @@ -82,6 +83,49 @@ class MultilayerPerceptronClassifierSuite
         }
       }
     
    +  test("strong dataset test") {
    +    val layers = Array[Int](4, 5, 5, 2)
    +
    +    val strongDataset = Seq(
    +      (Vectors.dense(1, 2, 3, 4), 0d, Vectors.dense(1d, 0d)),
    +      (Vectors.dense(4, 3, 2, 1), 1d, Vectors.dense(0d, 1d)),
    +      (Vectors.dense(1, 1, 1, 1), 0d, Vectors.dense(.5, .5)),
    +      (Vectors.dense(1, 1, 1, 1), 1d, Vectors.dense(.5, .5))
    +    ).toDF("features", "label", "expectedProbability")
    +    val trainer = new MultilayerPerceptronClassifier()
    +      .setLayers(layers)
    +      .setBlockSize(1)
    +      .setSeed(123L)
    +      .setMaxIter(100)
    +      .setSolver("l-bfgs")
    +    val model = trainer.fit(strongDataset)
    +    val result = model.transform(strongDataset)
    +    model.setProbabilityCol("probability")
    +    MLTestingUtils.checkCopyAndUids(trainer, model)
    +    // result.select("probability").show(false)
    +    result.select("probability", "expectedProbability").collect().foreach {
    +      case Row(p: Vector, e: Vector) =>
    +        assert(p ~== e absTol 1e-3)
    +    }
    +  }
    +
    +  test("test model probability") {
    +    val layers = Array[Int](2, 5, 2)
    +    val trainer = new MultilayerPerceptronClassifier()
    +      .setLayers(layers)
    +      .setBlockSize(1)
    +      .setSeed(123L)
    +      .setMaxIter(100)
    +      .setSolver("l-bfgs")
    +    val model = trainer.fit(dataset)
    +    model.setProbabilityCol("probability")
    +    val result = model.transform(dataset)
    +    val features2prob = udf { features: Vector => 
model.mlpModel.predict(features) }
    +    val cmpVec = udf { (v1: Vector, v2: Vector) => v1 ~== v2 relTol 1e-3 }
    +    assert(result.select(cmpVec(features2prob(col("features")), 
col("probability")))
    --- End diff --
    
    If this test fails, it will not give much info.  How about collecting the 
data and comparing on the driver?


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to